skyblasy Goto Github PK

followers: 4.0 following: 11.0 repos: 26.0 gists: 0.0

Name: S. Blasy

Type: User

Bio: Data Analyst and Scientist passionate about finding answers to business questions using statistics, machine learning, Python, and BI tools. Always learning!

Location: San Diego, California

S. Blasy's Projects

aws-lamda-csv-processing

Using AWS Lambda to automate and transform raw CSV Files for simple analysis

bi_analytics_with_kmeans

A business analysis of two brands and understanding their health by looking at relavant KPIs and using Kmeans Clustering

business_intelligence_with_python_and_ml

This repo has sample code and projects answering business questions such as market segmentation, churn, and survival analysis using Python, statistics, and machine learning

calculating_customer_lifetime_value

Using customer data to determine customer lifetime value using the lifetimes module and the BetaGeoFitter model

clustering_units_of_timeseries

Clustering units that have subsidiary time series

this repo houses the code and dataset to my article on medium which is on creating a bias free testset using stratified sampling split, rather than the conventional random split and selection which is broadly known as the train_test_split class in sklearn. link to the article here https://medium.com/@IrekponorVictor/creating-an-unbiased-test-set-for-your-model-using-stratified-sampling-technique-672b778022d5?source=user_profile---------2------------------

customer_churn_analysis

Churn analysis finding the factors to customer churn using machine learning algorithms and a simple artificial neural network

customer_segmentation_with_k-means_clustering

Customer segmentation analysis segmenting on frequency, recency, and monetary amount. This analysis is done with binning using quantiles and also unsupervised machine learning